Healx starting differential abundance workflow

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -17,6 +17,7 @@ body:
       description: A clear and concise description of what the bug is.
     validations:
       required: true
+
   - type: textarea
     id: command_used
     attributes:

.github/workflows/ci.yml

@@ -32,7 +32,7 @@ jobs:
           version: "${{ matrix.NXF_VER }}"
 
       - name: Run pipeline with test data
-        # TODO nf-core: You can customise CI pipeline run tests as required
+        # You can customise CI pipeline run tests as required
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |

.nf-core.yml

@@ -0,0 +1,6 @@
+repository_type: pipeline
+lint:
+  files_unchanged:
+    - assets/email_template.html
+    - assets/email_template.txt
+    - lib/NfcoreTemplate.groovy

README.md

@@ -12,7 +12,7 @@
 
 ## Introduction
 
-<!-- TODO nf-core: Write a 1-2 sentence summary of what data the pipeline is for and what it does -->
+**nf-core/differentialabundance** is a bioinformatics pipeline that can be used to analyse data represented as matrices, compararing groups of observations to generate differential statistics and downstream analayses. The initial feature set is built around RNA-seq, but we anticipate rapid expansion to include other platforms.
 
 **nf-core/differentialabundance** is a bioinformatics best-practice analysis pipeline for differential abundance analysis.
 
@@ -25,10 +25,10 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 ## Pipeline summary
 
-<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
-
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Generate a list of genomic feature annotations using the input GTF file.
+2. Cross-check matrices, sample annotations, feature set and contrasts to ensure consistency.
+3. Run differential analyis over all contrasts specified.
+4. Generate exploratory and differential analysis plots for interpretation.
 
 ## Quick Start
 
@@ -51,10 +51,8 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 4. Start running your own analysis!
 
-   <!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
-
    ```bash
-   nextflow run nf-core/differentialabundance --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
+   nextflow run nf-core/differentialabundance --input samplesheet.csv --contrasts contrasts.csv --matrix assay_matrix.tsv  --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
    ```
 
 ## Documentation

conf/base.config

@@ -10,7 +10,6 @@
 
 process {
 
-    // TODO nf-core: Check the defaults for all processes
     cpus   = { check_max( 1    * task.attempt, 'cpus'   ) }
     memory = { check_max( 6.GB * task.attempt, 'memory' ) }
     time   = { check_max( 4.h  * task.attempt, 'time'   ) }
@@ -24,7 +23,6 @@ process {
     //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
     //        If possible, it would be nice to keep the same label naming convention when
     //        adding in your local modules too.
-    // TODO nf-core: Customise requirements for specific processes.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
     withLabel:process_single {
         cpus   = { check_max( 1                  , 'cpus'    ) }
@@ -38,7 +36,7 @@ process {
     }
     withLabel:process_medium {
         cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
-        memory = { check_max( 36.GB * task.attempt, 'memory'  ) }
+        memory = { check_max( 2.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 8.h   * task.attempt, 'time'    ) }
     }
     withLabel:process_high {

conf/modules.config

@@ -13,26 +13,75 @@
 process {
 
     publishDir = [
-        path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+        path: { "${params.outdir}/${params.study_name}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
         mode: params.publish_dir_mode,
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: SAMPLESHEET_CHECK {
+    withName: GUNZIP_GTF {
         publishDir = [
-            path: { "${params.outdir}/pipeline_info" },
+            enabled: false
+        ]
+    }
+
+    withName: GTF_TO_TABLE {
+        publishDir = [
+            enabled: false
+        ]
+        ext.args = "--feature-type transcript"
+    }
+
+    withName: VALIDATOR {
+        publishDir = [
+            enabled: false
+        ]
+    }
+
+    withName: DESEQ2_DIFFERENTIAL {
+        publishDir = [
+            [
+                path: { "${params.outdir}/${params.study_name}/tables/differential" },
+                mode: params.publish_dir_mode,
+                pattern: '*.deseq2.results.tsv'
+            ],
+            [
+                path: { "${params.outdir}/${params.study_name}/tables/processed_counts" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{normalised_counts,vst,rlog}.tsv'
+            ],
+            [
+                path: { "${params.outdir}/${params.study_name}/plots/qc" },
+                mode: params.publish_dir_mode,
+                pattern: '*.png'
+            ],
+            [
+                path: { "${params.outdir}/${params.study_name}/tables/deseq2_other" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{rds,sizefactors.tsv,sessionInfo.log}'
+            ]
+        ]
+        ext.args = { "--vst_nsub 500 --contrast_variable $meta.variable --reference_level $meta.reference --treatment_level $meta.target --blocking_variables $meta.blocking" }
+    }
+    withName: PLOT_EXPLORATORY {
+        publishDir = [
+            path: { "${params.outdir}/${params.study_name}/plots/exploratory" },
             mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
+        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
+        ext.args = "--assay_names raw,normalised,variance_stabilised --final_assay variance_stabilised"
     }
 
-    withName: FASTQC {
-        ext.args = '--quiet'
+    withName: PLOT_DIFFERENTIAL {
+        publishDir = [
+            path: { "${params.outdir}/${params.study_name}/plots/differential" },
+            mode: params.publish_dir_mode,
+        ]
+        ext.args = { "--reference_level $meta.reference --treatment_level $meta.target" }
     }
 
     withName: CUSTOM_DUMPSOFTWAREVERSIONS {
         publishDir = [
-            path: { "${params.outdir}/pipeline_info" },
+            path: { "${params.outdir}/${params.study_name}/pipeline_info" },
             mode: params.publish_dir_mode,
             pattern: '*_versions.yml'
         ]

conf/test.config

@@ -20,10 +20,12 @@ params {
     max_time   = '6.h'
 
     // Input data
-    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
 
-    // Genome references
-    genome = 'R64-1-1'
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/mus_musculus/rnaseq_expression/SRP254919.samplesheet.csv'
+    matrix =  'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/mus_musculus/rnaseq_expression/SRP254919.salmon.merged.gene_counts.top1000cov.tsv'
+    contrasts =  'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/mus_musculus/rnaseq_expression/SRP254919.contrasts.csv'
+
+    // To do: replace this with a cut-down mouse GTF matching the matrix for testing
+    gtf = 'https://ftp.ensembl.org/pub/release-81/gtf/mus_musculus/Mus_musculus.GRCm38.81.gtf.gz'
+
 }

lib/WorkflowDifferentialabundance.groovy

@@ -13,10 +13,10 @@ class WorkflowDifferentialabundance {
         genomeExistsError(params, log)
 
 
-        if (!params.fasta) {
-            log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
-            System.exit(1)
-        }
+//        if (!params.fasta) {
+//            log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file."
+//            System.exit(1)
+//        }
     }
 
     //

main.nf

@@ -18,7 +18,7 @@ nextflow.enable.dsl = 2
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta')
+params.gtf = WorkflowMain.getGenomeAttribute(params, 'gtf')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

modules.json

@@ -5,25 +5,37 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "atlasgeneannotationmanipulation/gtf2featureannotation": {
+                        "branch": "master",
+                        "git_sha": "b5f51344caec9cbb7c0b650623069d5a254897a4"
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
                     "deseq2/differential": {
                         "branch": "master",
-                        "git_sha": "72900e24112957e65c53763f59ade5aca6322ea7"
+                        "git_sha": "46e4580ae2e6d361c2c026bb7466e807093a4e18"
                     },
-                    "fastqc": {
+                    "gunzip": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
+                    "shinyngs/staticdifferential": {
+                        "branch": "master",
+                        "git_sha": "36c30c95b8d3fa485939fdeca7325c98cdd9c73e"
+                    },
                     "shinyngs/staticexploratory": {
                         "branch": "master",
-                        "git_sha": "bf69d2f911a8aae8d06a6d3fa7ca8bf462c41e9e"
+                        "git_sha": "6d26aab1ab4fdeaabac866924dcfb4370ff5eeac"
+                    },
+                    "shinyngs/validatefomcomponents": {
+                        "branch": "master",
+                        "git_sha": "72695ee4b283a8f479fe503ee91d19fde160508f"
                     }
                 }
             }